LinkedIn Content Creation Skill by Reepl

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The setup explicitly tells the user to "Copy the API key shown after authorization" and to configure the MCP endpoint with ?key=YOUR_API_KEY, which instructs embedding a secret verbatim (as a query parameter), an insecure pattern that would require the agent to handle or include the raw secret.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads user-generated LinkedIn content (e.g., via get_saved_posts, get_collections, get_published_posts and the "browse your saved content library" patterns), so the agent ingests untrusted public social-media posts as part of its workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime calls to the Reepl MCP API (e.g. https://mcp.reepl.io/mcp?key=YOUR_API_KEY) to fetch the user's voice profile (userInstructions and generatedProfile), which are then used to directly control the agent's prompts and generation.